code-documenter

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands such as python -m doctest, pytest, and tsc --noEmit to verify that documentation examples are functional and follow type constraints.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx @redocly/cli to lint OpenAPI files, which involves fetching the Redocly CLI tool from the npm registry. Redocly is a well-known service provider in the documentation ecosystem.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes and executes content from external files.
  • Ingestion points: Source code, docstrings, and OpenAPI configuration files ingested from the user's project environment (SKILL.md).
  • Boundary markers: Absent; the workflow does not use delimiters or warnings to ignore embedded instructions in data.
  • Capability inventory: Executes arbitrary code snippets via doctest and pytest, and runs the Redocly CLI via npx (SKILL.md).
  • Sanitization: No explicit sanitization or filtering is applied to the content of the files before they are processed by the validation tools (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 10:43 AM
Security Audit — agent-trust-hub — code-documenter